Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuine behavioral context beyond that: results are returned 'newest first', and each row carries its conversion state, customer, and link. It stops short of describing pagination or auth behavior, but the ordering and row-shape disclosures are real value-adds.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the resource definition and return shape, then the filter surface, then the endpoint reference. No filler and nothing buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a no-required-param, read-only list tool with a fully documented schema and no output schema. The description supplies the return field preview and sort order, which is enough for an agent to call it correctly; only the omission of pagination nuance keeps it short of a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all nine parameters (page, limit, email, expand, affiliate_id, updated_since/until, conversion_state, stripe_customer_id) are already documented in the schema. The description enumerates the filter axes but adds no syntax or format detail beyond what the schema provides — the correct baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb (list) plus resource (referrals), and it goes further to define what a referral is — 'visitors who arrived via an affiliate link'. This definitional framing distinguishes it from sibling list tools like rewardful_list_commissions and rewardful_list_affiliates without the agent needing to open any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys the tool's scope (list referrals with filters by affiliate, state, email, Stripe customer, or updated-at window), which is enough to infer usage. However, it gives no explicit when-to-use/when-not guidance and never names a sibling as an alternative — nothing tells the agent to prefer this over, say, list_commissions for a given question.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.